Schwenck Johannes, Kneilling Manfred, Riksen Niels P, la Fougère Christian, Mulder Douwe J, Slart Riemer J H A, Aarntzen Erik H J G
Department of Nuclear Medicine and Clinical Molecular Imaging, Eberhard Karls University, Tübingen, Germany.
Department of Preclinical Imaging and Radiopharmacy, Werner Siemens Imaging Center, Eberhard Karls University, Röntgenweg 13, 72076, Tübingen, Germany.
Eur J Hybrid Imaging. 2022 Sep 1;6(1):17. doi: 10.1186/s41824-022-00138-1.
The detection of occult infections and low-grade inflammation in clinical practice remains challenging and much depending on readers' expertise. Although molecular imaging, like [F]FDG PET or radiolabeled leukocyte scintigraphy, offers quantitative and reproducible whole body data on inflammatory responses its interpretation is limited to visual analysis. This often leads to delayed diagnosis and treatment, as well as untapped areas of potential application. Artificial intelligence (AI) offers innovative approaches to mine the wealth of imaging data and has led to disruptive breakthroughs in other medical domains already. Here, we discuss how AI-based tools can improve the detection sensitivity of molecular imaging in infection and inflammation but also how AI might push the data analysis beyond current application toward predicting outcome and long-term risk assessment.
在临床实践中，隐匿性感染和低度炎症的检测仍然具有挑战性，并且很大程度上依赖于读者的专业知识。尽管分子成像技术，如[F]FDG PET或放射性标记白细胞闪烁扫描，能够提供关于炎症反应的定量且可重复的全身数据，但其解读仅限于视觉分析。这往往导致诊断和治疗延迟，以及潜在应用领域未被开发。人工智能（AI）提供了创新方法来挖掘丰富的成像数据，并且已经在其他医学领域带来了颠覆性突破。在此，我们讨论基于AI的工具如何能够提高分子成像在感染和炎症检测中的灵敏度，以及AI如何可能将数据分析从当前应用拓展至预测结果和长期风险评估。
